Extracting and supplementing method for EEG signal in manufacturing workshop based on deep learning of time–frequency correlation

Bin Ren () and Yunjie Pan
Additional contact information
Bin Ren: Shanghai University
Yunjie Pan: Shanghai University

Journal of Intelligent Manufacturing, 2023, vol. 34, issue 7, No 19, 3179-3196

Abstract: Abstract The quality of EEG signals is extremely important for brain–computer interface systems, especially in complex environments such as manufacturing floors. At present, there are few studies on the recovery methods of damaged EEG signals. Therefore, a TFCMI–CNN–LSTM hybrid model of time–frequency correlation analysis combined with deep learning is proposed to predict the missing data of EEG signals. We designed a brain fatigue experiment in a noisy environment to simulate the actual work situation of workers in the workshop, and verified the performance of the prediction model combined with the public EEG dataset BCI Competition IV 2a. The prediction results of the data set BCI Competition IV 2a show that the average RMSE between the prediction results of the TFCMI–CNN–LSTM model and the true value is 3.512, the MAE is 2.787, the Spearman Rank is 0.828, which can effectively restore abnormal EEG signals. This paper studies the importance of the CNN module in the model. The results show that the CNN module can greatly reduce the time spent in model training, and is more suitable for real-time EEG signal acquisition systems.

Keywords: EEG (electroencephalogram) signal; LSTM (long short term memory); Prediction model of the missing data; Manufacturing workshop (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-022-01997-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:34:y:2023:i:7:d:10.1007_s10845-022-01997-y

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-022-01997-y

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().